International Journal of Advances in Engineering & Scientific Research

International Journal of Advances in Engineering & Scientific Research

Print ISSN : 2349 –4824

Online ISSN : 2349 –3607

Frequency : Continuous

Current Issue : Volume 11 , Issue 1
2024


In current modern digital landscape, an exponential growth in the volumes and complexities of data inside enterprise networks calls for sophisticated security measures to mitigate and combat emerging cyber threats-primarily Distributed Denial of Service (DDoS) attacks. Honeypot systems, primarily in distributed environments, can be very effective in monitoring and tracking malicious activities; on the other hand, a traditional honeypot typically cannot handle the complexity in highly interactive environments and, therefore, sophisticated attacks. This work introduces a brand new approach using GenAI that is meant to enforce high-volume platform security: it utilizes the Self-Tuning Generative Adversarial Network-based Honeypot named STGAN-H. The detection and prevention of DDoS attacks by STGAN-H will be realized by the integration with several state-of-the art AI models, such as ARED, DHMM, and self-tuning GAN neural architectures to enhance the real-time recognition ability. The STGAN-H system, by simulating legitimate system behaviors, effectively deceives attackers while accurately identifying and neutralizing threats. Additionally, this framework incorporates deep learning techniques such as Restricted Boltzmann Machines (RBM), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks to enhance anomaly detection and response. The experimental results show that the proposed STGAN-H system achieves high detection accuracy in highly interactive environments and outperforms traditional machine learning and state-of-the-art deep learning-based models. This work emphasizes the need for GenAI in redefining enterprise cyber security and presents scalable, intelligent solutions for high-volume data platforms against increasingly complex attack vectors.

Keywords: Self-Tuning, DDoS, Honeypot, Deep Learning, Cyber security, Anomaly Detection, High-Volume Platforms and Enterprise Network.